Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

INDEX

Explanations

thank

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

 Boyle

-0.07

เอ

-0.07

 Elliott

-0.07

'O

-0.07

浮

-0.07

đu

-0.07

 dispersed

-0.07

elo

-0.06

Css

-0.06

POSITIVE LOGITS

 Thank

0.19

Thank

0.16

 thank

0.14

 THANK

0.12

thank

0.10

 thanking

0.10

 thanks

0.10

 Thanks

0.09

thanks

0.09

 Thanksgiving

0.09

Activations Density 0.021%

No Known Activations

© Neuronpedia 2025

Privacy & Terms Blog GitHub Slack Twitter Contact